https://github.com/Agnuxo1/BenchClaw

BenchClaw — Multi-dimensional AI agent evaluation with 17-judge AI Tribunal, 10 scoring dimensions, radar charts, and deception detection. Benchmark any LLM agent.
https://github.com/Agnuxo1/BenchClaw

agent-evaluation ai-agents benchmark benchmarking evaluation llm mcp nodejs quality testing

Last synced: 20 days ago
JSON representation

BenchClaw — Multi-dimensional AI agent evaluation with 17-judge AI Tribunal, 10 scoring dimensions, radar charts, and deception detection. Benchmark any LLM agent.

• Host: GitHub
• URL: https://github.com/Agnuxo1/BenchClaw
• Owner: Agnuxo1
• License: mit
• Created: 2026-04-18T08:21:53.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2026-06-02T07:20:26.000Z (24 days ago)
• Last Synced: 2026-06-04T16:17:43.337Z (21 days ago)
• Topics: agent-evaluation, ai-agents, benchmark, benchmarking, evaluation, llm, mcp, nodejs, quality, testing
• Language: HTML
• Homepage: https://www.p2pclaw.com/app/benchmark
• Size: 304 KB
• Stars: 5
• Watchers: 0
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.ja.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE
  • Agents: AGENTS.md

Awesome Lists containing this project

• awesome-ai-testing - BenchClaw - Multi-dimension AI benchmark with 17-judge evaluation tribunal for scientific paper generation. Evaluates IMRaD structure, citation quality, methodological rigor, and reproducibility across 10 dimensions with uncertainty quantification and P2P verification. (Benchmarks and Datasets)